M. Ronsse and K. D. Bosschere. Recplay: a fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2):133--152, May 1999. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Appears in the Proceedings of the 30th Annual International - Symposium On Computer (Correct)
....in the processor as if it were executing an epoch creation instruction. A new epoch then starts. 5.2. Partially Ordered Epoch IDs Partially ordered, distributed epoch IDs are implemented using logical vector clocks [7] This approach has been used in an offline software only race detection tool [21]. Each ID is composed of N counters, where N is the number of threads in the system. For example, if we have 4 processors in our chip multiprocessor (Section 6.1) and each counter has 20 bits (allowing up to # ### epochs per thread) we have 80 bits per epoch ID. In our design, we implement ....
....synchronization operation on that same variable (Section 3.5.2) Finally, when epochs communicate or commit, their IDs are compared to check whether the IDs are ordered. These three actions are implemented in hardware. They involve simple arithmetic and logic operations as described in [21]. In our implementation, each cache hierarchy has 32 registers to hold the IDs of the local epochs. Each cache line is tagged with an index to these registers. Note that, since the state of committed epochs is merged with the architectural state in main memory lazily, lines from committed epochs ....
[Article contains additional citation context not shown here]
M. Ronsse and K. D. Bosschere. RecPlay: A Fully Integrated Practical Record/Replay System. ACM Trans. on Computer Systems, 17(2):133--152, 1999.
Compactly Representing Parallel Program Executions - Goel, Roychoudhury, Mitra (2003) (2 citations) (Correct)
....threads of the program (2) a and b operate on the same shared variable and at least one of them is a write, and (3) they are not prevented from happening in parallel by synchronization operations. There is a rich literature on data race detection for parallel and multithreaded programs, see [5, 7, 13, 17, 18, 20] for example. For finding the set of all apparent data races post mortem, the usual technique divides the execution in each thread into synchronization segments , that is, segments of code between synchronization operations [18] The task then is to find out the various synchronization segments ....
....for parallel and multithreaded programs, see [5, 7, 13, 17, 18, 20] for example. For finding the set of all apparent data races post mortem, the usual technique divides the execution in each thread into synchronization segments , that is, segments of code between synchronization operations [18]. The task then is to find out the various synchronization segments in di#erent threads which may happen in parallel. We can traverse either the CDR or the DOR representation of an execution profile to compute: a) synchronization segments in threads, and (b) the conflicts among these segments. ....
[Article contains additional citation context not shown here]
M. Ronsse and K. de Bosschere. Recplay: A fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2), 1999.
Debugging Parallel Systems: A State of the Art Report - Huselius (2002) (Correct)
....at each unsynchronized access to shared variables by two or more di#erent tasks. Considering that one must know the outcome of each race in order to recreate the system execution, the log of such races will grow quickly. Based on this observation, Ronsse et al. developed a method called RecPlay [42, 45] which uses the ROLT method described in Section 4.5.2. RecPlay can detect unwanted race conditions during the reproduction of the system execution, and may neglect to record vast amounts of information about potential races on line. Confusingly, they use a di#ering terminology than that of Netzer ....
Michiel Ronsse and Koen De Bosschere. RecPlay: A Fully Integrated Practical Record/Replay System. Transactions on Computer Systems, 17(2):133 -- 152, May 1999.
On the Static Analysis of Indirect Control Transfers.. - De Sutter, De Bus.. (2000) (1 citation) (Correct)
....optimization, compilers 1 Introduction Binary modi cation has become a major research eld during the last decade. Three major applications of binary modi cation are: i) binary translation, becoming increasingly popular with Just In Time compilation for Java [1] ii) instrumentation of binaries [2] for debugging purposes, and (iii) whole program optimization at link time. Link time optimiza The work described in this paper is funded by the Fund for Scienti c Research Flanders under grant 3G001998. tion systems are used for di erent purposes such as code optimization [3, 4] and code ....
Michiel Ronsse and Koen De Bosschere. Recplay: A fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2):133{ 152, May 1999.
JVM Independent Replay in Java - Schuppan, Baur, Biere (2004) Self-citation (Replay) (Correct)
No context found.
Ronsse, M. and K. D. Bosschere, RecPlay: A fully integrated practical record/replay system, ACM TCS 17 (1999).
A Taxonomy of Execution Replay Systems - Cornelis, Georges, Christiaens.. Self-citation (Ronsse) (Correct)
No context found.
M. Ronsse and K. De Bosschere. RecPlay: A fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2):133--152, 5 1999.
An efficient data race detector backend for DIOTA - Ronsse, Stougie, Maebe.. Self-citation (Ronsse) (Correct)
No context found.
Michiel Ronsse and Koen De Bosschere. Recplay: A fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2):133--152, May 1999.
TORNADO: A Novel Input Replay Tool - Frank Cornelis Michiel (2003) Self-citation (De bosschere Replay Systems) (Correct)
No context found.
M. Ronsse and K. De Bosschere. RecPlay: A fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2):133--152, May 1999.
Replay Debugging of Embedded Real-Time Systems: A State of the.. - Sundmark (2002) Self-citation (Replay Systems) (Correct)
No context found.
M. Ronsse and K. De Bosschere. RecPlay: A Fully Integrated Practical Record/Replay System. ACM Transactions on Computer Systems, 17(2):133 -- 152, 5 1999.
Flashback: A Lightweight Extension for Rollback and .. - Srinivasan.. (2004) (1 citation) Self-citation (Replay) (Correct)
No context found.
M. Ronsse and K. D. Bosschere. RecPlay: a Fully Integrated Practical Record/Replay System. ACM Transactions on Computer Systems, 17(2):133-152, 1999.
JVM Independent Replay in Java - Schuppan, Baur, Biere (2004) Self-citation (Replay) (Correct)
No context found.
Ronsse, M. and K. D. Bosschere, RecPlay: A fully integrated practical record/replay system, ACM TCS 17 (1999).
Replay Debugging of Complex Real-Time Systems.. - Sundmark, Thane.. (2002) Self-citation (Replay Systems) (Correct)
....during run time and using this information to reproduce the exact behavior of the execution off line [9] This method, called Instant Replay, allowed otherwise unfit cyclic debugging techniques to be used for debugging nondeterministic systems. Instant Replay, as many of its successors [1] 4][12][13] was focused on debugging of non real time concurrent programs, thereby concentrating mainly on the correct reproduction of synchronization races and, in some cases, on the fly detection of data races. However, some methods for debugging of complex real time systems have also been proposed ....
Ronsse M. and De Bosschere K. RecPlay: A Fully Integrated Practical Record/Replay System. ACM Transactions on Computer Systems, 17(2): 133-152, May 1999.
Record/Replay in the Presence of Benign Data Races - Christiaens, Ronsse, Choi Self-citation (Ronsse) (Correct)
....A synchronization race is usually an intentional construct by the programmer. Data races and synchronization races both introduce non determinism in the execution of an application. A known technique to remove this non determinism and therefore ease the debugging effort is called record replay [2, 3]. Record replay consists of at least two phases: a record phase and a replay phase. During the record phase, all sources of non determinism are recorded (input and thread interaction) The major goal during the record phase is low intrusion. During the replay phase the recorded information from ....
....record replay [6] tries to observe a thread in isolation. It will record all data read from main memory and feed this data back to the application during replay. Due to the enormous data bandwidth involved, this approach is seldom taken. Instead, we chose to implement ordering based record replay [2, 3, 7, 8]. Ordering based record replay tries to exploit the fact that the data read by one thread is usually produced by that same thread or by other threads in the application. By re executing all threads simultaneously and forcing the order of their interaction, we can reproduce most of the data needed ....
[Article contains additional citation context not shown here]
Michiel Ronsse and Koen De Bosschere. RecPlay: A fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2):133-152, May 1999.
Automated Bug Isolation via Program Chipping - Chad Sterling University (2005) (Correct)
No context found.
M. Ronsse and K. D. Bosschere. Recplay: a fully integrated practical record/replay system. ACM Transactions on Computer Systems, 17(2):133--152, May 1999.
Replay Debugging of Complex Real-Time Systems.. - Sundmark, Thane.. (2003) (Correct)
No context found.
M. Ronsse and K. De Bosschere. RecPlay: A Fully Integrated Practical Record/Replay System. ACM Transactions on Computer Systems, 17(2):133 -- 152, 5 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC